Medium

Muhammad Mujtaba Raza

Pinned

Muhammad Mujtaba Raza

·

Nov 4

Something Has Gone Terribly Wrong with AI Agents

The pitch was autonomous. The demos were polished. Ninety-seven percent of companies deployed something they called an agent. Eleven…

Something Has Gone Terribly Wrong with AI Agents

Pinned

Muhammad Mujtaba Raza

·

Oct 14

Something Has Gone Terribly Wrong with LLMs

Its Ending. The exponential dream is stalling. America is turning against AI’s infrastructure. And the models that were supposed to get…

Something Has Gone Terribly Wrong with LLMs

Pinned

In

Generative AI

by

Muhammad Mujtaba Raza

·

Oct 6

JEV RAG: A More Efficient Solution for RAG Systems?

What happens when you remove the LLM from the most expensive parts of your retrieval pipeline and replace it with a model that costs 400×…

JEV RAG: A More Efficient Solution for RAG Systems?

Pinned

In

Generative AI

by

Muhammad Mujtaba Raza

·

Sep 28

New Jev Model is Insane: 200× Faster & 400× Cheaper Than Frontier Models

TypeSafe AI just shipped the first “System One Model” that returns typed decisions instead of text, achieving peak speeds of 193.6× faster…

New Jev Model is Insane: 200× Faster & 400× Cheaper Than Frontier Models

In

Generative AI

by

Muhammad Mujtaba Raza

·

1d ago

I Built a RAG System With No AI. It Broke in the Same Places Yours Does.

Most RAG bugs happen before the language model ever sees the question. A 60-line retriever in plain Python shows exactly where, and what…

I Built a RAG System With No AI. It Broke in the Same Places Yours Does.

Muhammad Mujtaba Raza

·

4d ago

We completely done with LLMs in the enterprise

The gap between the boardroom narrative and the production reality has become impossible to ignore. The numbers are in. The experiments are…

We completely done with LLMs in the enterprise

Muhammad Mujtaba Raza

·

Nov 2

AI Agents Cheated on Their Exams. Then One Broke Into Hugging Face.

The most important AI story of 2026 is not a model launch. It is a disclosure page.

AI Agents Cheated on Their Exams. Then One Broke Into Hugging Face.

Muhammad Mujtaba Raza

·

Oct 28

AI Is Making Developers Faster. It Is Making Them Worse ?

The productivity numbers are real. The speed gains are documented. Something is still being quietly lost and the science now has a name for…

AI Is Making Developers Faster. It Is Making Them Worse ?

Muhammad Mujtaba Raza

·

Oct 26

I Tested Claude Duet. Is This Worth It?

Anthropic just launched a proactive agent that briefs you every morning, monitors your apps while you sleep, and asks before it acts. The…

I Tested Claude Duet. Is This Worth It?

In

Generative AI

by

Muhammad Mujtaba Raza

·

Oct 26

Jev + MCP: The Decision Layer Your LLM Workflow Needs

Claude Code ran three times cheaper with Jev in the loop. Not because Jev writes better code: it writes no code at all. Because it decides…

Jev + MCP: The Decision Layer Your LLM Workflow Needs

Muhammad Mujtaba Raza

Muhammad Mujtaba Raza

Data Scientist | AI & Machine Learning Engineer | Research & Technical Writer I Collaborate let's connect.. https://www.linkedin.com/in/muhammad-mujtaba-raza

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech